b5
@b5.bsky.social
Worker crayon at n0.computer, we make iroh.computer
I'm on Germ DM 🔑
anchr://ger.mx/A9A0GsjAZe-wyCuxCrgHSURalNt31l2S111tgN84609u#did:plc:oogtn2wrdtfm4wgxemfxenn4
I'm on Germ DM 🔑
anchr://ger.mx/A9A0GsjAZe-wyCuxCrgHSURalNt31l2S111tgN84609u#did:plc:oogtn2wrdtfm4wgxemfxenn4
Even for generated code, this is dog water
November 1, 2025 at 1:13 AM
Even for generated code, this is dog water
Me: “@copilot UNSUBSCRIBE”
Copilot: “Sure thing b5, you’re so right. I’ve gone ahead and cancelled your GitHub account! 🚀”
Copilot: “Sure thing b5, you’re so right. I’ve gone ahead and cancelled your GitHub account! 🚀”
October 29, 2025 at 5:48 PM
Me: “@copilot UNSUBSCRIBE”
Copilot: “Sure thing b5, you’re so right. I’ve gone ahead and cancelled your GitHub account! 🚀”
Copilot: “Sure thing b5, you’re so right. I’ve gone ahead and cancelled your GitHub account! 🚀”
seriously, why on earth can't I dismiss this message?
Twitter dying I can live with. The enshitification of github–however-is a material problem.
Twitter dying I can live with. The enshitification of github–however-is a material problem.
October 29, 2025 at 1:33 PM
seriously, why on earth can't I dismiss this message?
Twitter dying I can live with. The enshitification of github–however-is a material problem.
Twitter dying I can live with. The enshitification of github–however-is a material problem.
Yep yep yep 💯, i like the active vs passive language.
In security circles “trust on first use” is seen as a very bad thing, but strikes me as exactly the right thing here: spend as little of the user’s active trust as possible: by delegating to a secure, passive, zero trust protocol
In security circles “trust on first use” is seen as a very bad thing, but strikes me as exactly the right thing here: spend as little of the user’s active trust as possible: by delegating to a secure, passive, zero trust protocol
October 28, 2025 at 12:11 PM
Yep yep yep 💯, i like the active vs passive language.
In security circles “trust on first use” is seen as a very bad thing, but strikes me as exactly the right thing here: spend as little of the user’s active trust as possible: by delegating to a secure, passive, zero trust protocol
In security circles “trust on first use” is seen as a very bad thing, but strikes me as exactly the right thing here: spend as little of the user’s active trust as possible: by delegating to a secure, passive, zero trust protocol
It’s a tragedy of the name. Zero trust is a means of strengthening bonds between people: it maintains human expectations about computer behavior
October 28, 2025 at 10:56 AM
It’s a tragedy of the name. Zero trust is a means of strengthening bonds between people: it maintains human expectations about computer behavior
It’s a thing. podcasts.apple.com/us/podcast/t...
The Spotify Effect, Pt 1: Ghosts in the Playlist
Podcast Episode · Close All Tabs · 06/04/2025 · 34m
podcasts.apple.com
October 21, 2025 at 4:27 AM
It’s a thing. podcasts.apple.com/us/podcast/t...
Reposted by b5
P.S. I linked to @rklaehn.bsky.social's twitter post above, but here's his bsky post: bsky.app/profile/rkla...
I recently got nerdsniped by @zooko2.bsky.social
into implementing fast BLAKE3 hashing of multiple small blobs.
I wrote a blog post about my experiment.
iroh.computer/blog/hashing...
It would be cool to polish this a bit and turn it into a public API.
into implementing fast BLAKE3 hashing of multiple small blobs.
I wrote a blog post about my experiment.
iroh.computer/blog/hashing...
It would be cool to polish this a bit and turn it into a public API.
Hashing multiple blobs with BLAKE3
How to quickly hash multiple small blobs with BLAKE3
iroh.computer
October 15, 2025 at 5:46 PM
P.S. I linked to @rklaehn.bsky.social's twitter post above, but here's his bsky post: bsky.app/profile/rkla...